© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174961
    Prev
    Next
    INDEX
    Explanations

    get_ function calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     abrasive
    0.45
     trasc
    0.43
     분석
    0.41
     illustrazione
    0.41
     memcpy
    0.40
     copiar
    0.39
    ឧ
    0.39
     eminently
    0.38
    alura
    0.38
     భా
    0.38
    POSITIVE LOGITS
     Protest
    0.40
    +$
    0.40
    event
    0.40
    indicate
    0.39
    Attendance
    0.39
    eeee
    0.38
    Tony
    0.38
     добро
    0.38
    Celebrating
    0.38
     காட்சிகள்
    0.38
    Activations Density 0.001%

    No Known Activations